{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3U5LCPTS7VR3LINSXZA2LK6PMM","short_pith_number":"pith:3U5LCPTS","schema_version":"1.0","canonical_sha256":"dd3ab13e72fd63b5a1b2be41a5abcf631677be70f0f646d950f35a04ad1f4b6f","source":{"kind":"arxiv","id":"2505.13809","version":5},"attestation_state":"computed","paper":{"title":"Semiparametric Off-Policy Inference for Optimal Policy Values under Possible Non-Uniqueness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.EM","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Haoyu Wei","submitted_at":"2025-05-20T01:41:44Z","abstract_excerpt":"Off-policy evaluation (OPE) constructs confidence intervals for the value of a target policy using data generated under a different behavior policy. Most existing inference methods focus on fixed target policies and may fail when the target policy is estimated as optimal, particularly when the optimal policy is non-unique or nearly deterministic.\n  We study inference for the value of optimal policies in Markov decision processes. In an auxiliary augmented transition-sampling experiment, we characterize the existence of the efficient influence function and show that non-regularity arises when c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.13809","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2025-05-20T01:41:44Z","cross_cats_sorted":["econ.EM","stat.ML","stat.TH"],"title_canon_sha256":"4565f2b60f05ced5b3c49d441ec3c396c01bfd6b7299e9d5111c6e5948706d1e","abstract_canon_sha256":"a5e83299de933ad94829046dd242630e7c24dc71e05523e2dfaed3a7f0ab5418"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:13:59.937303Z","signature_b64":"33bLV7yLJXfl/dL8Hs6sv2vt1h22+Nm08L63Lk7/eGgKM3QpNOkhh6TLy3qBkZIkMdX7KVnskWdAOugGaq3ICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd3ab13e72fd63b5a1b2be41a5abcf631677be70f0f646d950f35a04ad1f4b6f","last_reissued_at":"2026-06-29T00:13:59.936846Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:13:59.936846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semiparametric Off-Policy Inference for Optimal Policy Values under Possible Non-Uniqueness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.EM","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Haoyu Wei","submitted_at":"2025-05-20T01:41:44Z","abstract_excerpt":"Off-policy evaluation (OPE) constructs confidence intervals for the value of a target policy using data generated under a different behavior policy. Most existing inference methods focus on fixed target policies and may fail when the target policy is estimated as optimal, particularly when the optimal policy is non-unique or nearly deterministic.\n  We study inference for the value of optimal policies in Markov decision processes. In an auxiliary augmented transition-sampling experiment, we characterize the existence of the efficient influence function and show that non-regularity arises when c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13809","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.13809/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.13809","created_at":"2026-06-29T00:13:59.936903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13809v5","created_at":"2026-06-29T00:13:59.936903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13809","created_at":"2026-06-29T00:13:59.936903+00:00"},{"alias_kind":"pith_short_12","alias_value":"3U5LCPTS7VR3","created_at":"2026-06-29T00:13:59.936903+00:00"},{"alias_kind":"pith_short_16","alias_value":"3U5LCPTS7VR3LINS","created_at":"2026-06-29T00:13:59.936903+00:00"},{"alias_kind":"pith_short_8","alias_value":"3U5LCPTS","created_at":"2026-06-29T00:13:59.936903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3U5LCPTS7VR3LINSXZA2LK6PMM","json":"https://pith.science/pith/3U5LCPTS7VR3LINSXZA2LK6PMM.json","graph_json":"https://pith.science/api/pith-number/3U5LCPTS7VR3LINSXZA2LK6PMM/graph.json","events_json":"https://pith.science/api/pith-number/3U5LCPTS7VR3LINSXZA2LK6PMM/events.json","paper":"https://pith.science/paper/3U5LCPTS"},"agent_actions":{"view_html":"https://pith.science/pith/3U5LCPTS7VR3LINSXZA2LK6PMM","download_json":"https://pith.science/pith/3U5LCPTS7VR3LINSXZA2LK6PMM.json","view_paper":"https://pith.science/paper/3U5LCPTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13809&json=true","fetch_graph":"https://pith.science/api/pith-number/3U5LCPTS7VR3LINSXZA2LK6PMM/graph.json","fetch_events":"https://pith.science/api/pith-number/3U5LCPTS7VR3LINSXZA2LK6PMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3U5LCPTS7VR3LINSXZA2LK6PMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3U5LCPTS7VR3LINSXZA2LK6PMM/action/storage_attestation","attest_author":"https://pith.science/pith/3U5LCPTS7VR3LINSXZA2LK6PMM/action/author_attestation","sign_citation":"https://pith.science/pith/3U5LCPTS7VR3LINSXZA2LK6PMM/action/citation_signature","submit_replication":"https://pith.science/pith/3U5LCPTS7VR3LINSXZA2LK6PMM/action/replication_record"}},"created_at":"2026-06-29T00:13:59.936903+00:00","updated_at":"2026-06-29T00:13:59.936903+00:00"}